**7. Type 2 Diabetes as a case study**

suggested methodology. The previously discussed methods suffer from some limitations in addressing imbalance issues, complex and temporal relationships between (sometimes unmeasured) factors, and the identification of different underlying characteristics of disease for different subgroups of the population. There is considerable research on predicting T2DM complications. Among these, studies on explaining unknown risk factors and identifying temporal phenotypes by using

*Type 2 Diabetes - From Pathophysiology to Cyber Systems*

*The proposed hybrid methodology to find explainable subgroup of patients by personalising diabetic patients in precision medicine. This figure is an abstract methodology explained in Figures 1–4 in the previous*

**Figure 2.**

**210**

*work in [83].*

The World Health Organisation (WHO) reported that Type 2 Diabetes Mellitus (T2DM) accounts for at least 90% of all diabetes types. Another study in WHO revealed that T2DM patients are at increased risk of long-term vascular comorbidities, which is known as "underlying cause of death" and severe phenotype of the disease [86]. It has previously been observed that patients with T2DM are also at an increased risk of microvascular comorbidities, including nephropathy, neuropathy, and retinopathy [86]. Similar to Diabetic type 1 patients, although genetic factors impact on developing T2DM, it is believed ignorance of developing complications harms patient life because it may develop a different profile of complications and features, which changes over time per follow-up visit. However, these life-threatening complications remain undiagnosed for a long time because of the hidden patterns of their associated risk factors [11]. The underlying pattern of the complications is known as the major source of mortality and morbidity in T2DM and how their co-occurrence is followed/caused by other complications associated with the disease [64]. That is because predicting a target complication can be challenging without the consideration of the effects of its associated complications.

#### **7.1 Data description**

The observed dataset in this chapter is similar to the data utilised in the previous study of Diabetes patients in [83] of pre-diagnosed T2DM patients aged twenty five to sixty five years (inclusive) that were recruited from clinical followups at the "IRCCS Instituti Clinic Scientifici" (ICS) Maugeri of Pavia, Italy. The MOSAIC project funds the information based on the seventh Framework Program of the European Commission, Theme ICT201152 Virtual Physiological Human (600914) from 2009 to 2013. These consists of physical examinations and laboratory data for complications and risk factors (predictors) in T2DM which were selected supported existing literature on T2DM [76, 87–90] as well as the recommendations from the clinicians at ICS. These are Retinopathy (RET), Hypertension (HYP), Nephropathy (NEP), Neuropathy (NEU) and LIVer disease (LIV) (see **Table 1**). Here, the predictors are known and selected from the dataset: Body Mass Index (BMI), Systolic Blood Pressure (SBP), High-density Lipoprotein (HDL), Glycated Haemoglobin (HbA1c or HBA), Diastolic Blood pressure (DBP), ChOLesterol (COL), Smoking habit (SMK) and Creatinine (CRT). Control Values for T2DM risk factors are classified in **Table 2** illustrates three clinical level of risk, particularly low (zero), medium (one) and high (two). In T2DM data, the worsening level of the microvascular diseases and HYP is known as a significant cause of death [91]. Even though micro-vascular complications such as RET, NEP, NEU are less frequent comparing to HYP, an inadequate estimation of them causes long-term suffering

#### *Type 2 Diabetes - From Pathophysiology to Cyber Systems*


classification problems with more than two targets including high, medium, and low risk patient, according to a diabetes experts definitions [95, 96]. For each patient in T2DM dataset, time-series analysis is described in Appendix A with

*Predicting Type 2 Diabetes Complications and Personalising Patient Using Artificial…*

This section summarises the clinical implications and shows how the obtained experimental findings in the previous works [83, 84, 97] and their significance have led to developing explanatory AI models. For example **Table 3** illustrated the promising results obtained by the proposed Stepwise approach discussed in [33, 84].

In **Table 4**, the prediction performance of the underlying patterns of complications for these patients within the discovered subgroup dataset (was introduced in [83] as DS1 and discovered using the descriptive strategy) was analysed and compared to all patients belonged to DS (the raw T2DM dataset). It also suggested that DS1 (by personalising patients) could be considered as a dataset with less uncertainty than DS. In order to describe the inference problem in this chapter, the causal relationships seemed to be a reliable option to represent static and dynamic correlations between T2DM risk factors. The causal inference has a greater focus on distinguishing causes from other associations than on uncovering detailed temporal relationships. Therefore, in this work ([83]), several predictive strategies in order to

**Percentage (%) Accuracy Sensitivity Specificity Precision** No Hidden variable in [32] 48 53 48 53 Stepwise IC\* in [33] (Step1) 60 40 80 70 Enhanced stepwise in [97] (Step1) 80 51 98 97 Stepwise IC\* in [33] (Step2) 78 98 58 68 Enhanced stepwise in [97] (Step2) 95 80 96 86 Stepwise IC\* in [33] (Step3) 78 98 58 68 Enhanced stepwise in [97] (Step3) 95 81 96 82 Enhanced stepwise in [97] (Step4) 96 81 97 092 Enhanced stepwise in [97] (Step5) 95 82 97 85

*Comparison of our new and enhanced stepwise IC\*LS approach in [97] with its previous version (stepwise IC\*)*

**DS DS1**

**Complication Accuracy**

NEP 0.81 0.93 LIV 0.77 0.88 HYP 0.91 0.99 NEU 0.76 0.81 RET 0.81 0.79 All 0.81 0.88

*The overall prediction accuracy of T2DM complications for patients in DS is compared to DS1.*

definition of the related notations.

*DOI: http://dx.doi.org/10.5772/intechopen.94228*

**Table 3.**

**Table 4.**

**213**

*in [33] and without latent variable in [32].*

**8. Experimental results and conclusions**

#### **Table 1.**

*The description of T2DM target complication, clinical node control values, and discretised states [83].*


#### **Table 2.**

*The description of the T2DM clinical features, risk factors, control values, and the discretised states [83].*

and life-threatening comorbidities [64]. Fowler and co-authors in [7] researched type 2 Diabetic American patients. This research utilised T2DM key risk factors such as HbA1c, SBP, and DBP to investigate relationships among complications such as HYP, NEP, RET, and NEU. In addition, LIV is a severe phenotype of diabetes and associated with T2DM complications, especially NEU [92]. Litwak analysed Russian diabetic patients in [93] which referred to the influence of macrovascular and micro-vascular disease on one anther. For example, important features in T2DM dataset such as blood pressure, HDL, lipid, BMI, and HbA1c influence diabetic patients' complications. They also revealed that HDL has a negative effect on HYP, NEP, NEU, and RET, whereas HbA1c negatively associated with HYP. Again, a study conducted by Ramachandran [94] referred to the high prevalence of NEU and RET in Type 2 diabetes in India. Similarly, research in [76] suggested that most of the diabetic patients have objective evidence for some variety of NEU, but only a few of them have identified by symptoms. This research also showed that there is a strong association among NEP, NEU, and RET. This study only concentrates on five binary complications as the predictive target classes in a binary classification problem (with two categories of classes: "high" or "low" risk). Furthermore, a complication class value of low risk (zero) represents a patient visit in which the complication is not present; otherwise, it is at high risk (one). For instance, a complication class value of zero represents a patient visit in which the complication is not present; otherwise, it is one. Alternatively, other risk factors associated with a patient (symptoms/clinical tests) are abstracted in the multi-class

*Predicting Type 2 Diabetes Complications and Personalising Patient Using Artificial… DOI: http://dx.doi.org/10.5772/intechopen.94228*

classification problems with more than two targets including high, medium, and low risk patient, according to a diabetes experts definitions [95, 96]. For each patient in T2DM dataset, time-series analysis is described in Appendix A with definition of the related notations.
